全局渐近稳定的一类变时多时滞神经网络模型  

Global asymptotic stability of a class of neural networks with multiple time-varying delays

作　　者：王姗姗[1] 王拉省[1] 

机构地区：[1]西安工程大学理学院,陕西西安710048

出　　处：《纺织高校基础科学学报》2008年第3期342-345,共4页Basic Sciences Journal of Textile Universities

基　　金：西安工程大学校管项目(2007XG32;XJG07009)

摘　　要：研究了一类变时滞神经网络的渐近稳定性问题.利用线性矩阵不等式和构造适当的Lya-punov函数,给出了该模型的平衡点惟一性和全局渐近稳定的新判据.与现有的一些文献中的结果相比,考虑了神经元激励和抑制的影响,所得的判据保守性小,适用范围宽.Global asymptotical stability of a class of neural networks with multiple time-varying delays was studied. On the basis of LMI inequality technique and properly built Lyapunov funetion,a new sufficient criteria is given to ensure the global asymptotical stability for the equilibrium points in relevant neural networks. Compared with some results in earlier works,the obtained criteria are less conservative and wider in application, and can eliminate the difference between the neuronal excitatory and inhibitory effects.

关 键 词：神经网络 变时滞 多时滞 LYAPUNOV函数 

分 类 号：O29[理学—应用数学]